Seminar "Machine Learning in Robot Assisted Therapy (RAT)"

Organizer: M.Sc. Sina Shafaei

Contact: shafaei (at) in.tum.de

Modul: IN2107

Registration: Via Matching System

Type: MasterSeminar

Semester: SS 2018

ECTS: 5.0/4.0

Time & Location: 02.09.023 / 15:00-17:00


News

  • The first session of the seminar (details, topic assignments, team members) will be on 20.04.2018 at 02.09.023, 15:00-17:00

  • Registration is only via Matching System, 09.02-20.02, and there is no need to submit any document (C.V, motivation letter, etc.) beforehand


Content

Autism Spectrum Disorders (ASD) is characterized by impairments in social interactions and communication, usually accompanied by restricted interests and behavior. Most of the individuals with ASD require professional care throughout their lives, entailing a significant financial and time (at least 15 hours per week) commitment.

Communication of the autistic people has also some differences which might lead to being misunderstood by the others. For example, people with ASD have difficulties in reading social cues, facial expressions and voice inflection. Therefor, it’s highly advised by the trainers to emphasis on the real meaning of the words instead of implicit or metaphorical ways, since it’s the only trusted mean of inferring and communicating. According to the recent researches, detecting the ASD in the early ages would help to control and adopt the behavioral aspects of the autistic kids in order to prepare them for entering the society. The main objective of a trainer is to make the knowledge for the kid. Knowledge prepares the backbone of understanding and following that acceptance comes form the kid. the interaction between autistic people and the others is in controlling the body, thought process, senses and communication.

The aim of this seminar is to increase knowledge on therapy and educational objectives professionals work on with children with autism spectrum disorder (ASD) and to identify corresponding state of the art robots. One of the main objectives of this seminar is to have an investigation on different levels of autonomy of these robots which can be handled by numerous machine learning-based approaches.


Structure

In our first session (20.04.2018) we will distribute the topics among the groups of students (groups of two members). Groups will collect the necessary materials (state of the art scientific works like publications) within the context of their topic and will perform their research based on the collected resources. Each group will be given 40 minutes on their specified date (are listed in below) to represent their results and afterwards will write and submit a scientific paper (IEEE template) with minimum 6 pages, explaining the main contributions of their work in this seminar.


                                  TopicsPresentation (Date) Slides
A- Impact of Robot Tutor (Nonverbal Social Behavior) on Child Learning29.06.2018slides
B- Increasing the Autonomy Level of the RAT-based Robots with Machine Learning, Use Cases and Approaches29.06.2018 slides
C- Trends in Robot Assisted Therapy (RAT) and Robot Enhanced Therapy (RET)06.07.2018 slides
D- Applications of Supervised, Unsupervised and Reinforcement Learning in RAT, Approaches06.07.2018 slides
E- Reward Processing in Autism and Reinforcement Learning13.07.2018 slides
F- Machine Learning Frameworks for Teaching Social Skills to Children with Autism13.07.2018slides
G- Behavior Control Architectures for Social Robots20.07.2018
H- Adaptive robot-Mediated Intervention Architectures20.07.2018
I- Ensuring the Safety of an Autonomous Robot in Interaction with Children, Challenges and Considerations27.07.2018
J- Ensuring the Safety of an Autonomous Robot in Interaction with Children, Vision, Methods and Approaches27.07.2018
K- Leveraging Human Inputs in Interactive Machine Learning for Human Robot Interaction03.08.2018
L- Autonomous Robots and Ethical Issues When Working with Children03.08.2018

Material